Estimation of the energy of a PV generator using artificial neural network

The integration of grid-connected photovoltaic (GCPVS) systems into urban buildings is very popular in industrialized countries. Many countries enhance the international collaboration efforts which accelerate the development and deployment of photovoltaic solar energy as a significant and sustainable renewable energy option. A previous method, based on artificial neural networks (ANNs), has been developed to electrical characterisation of PV modules. This method was able to generate V-1 curves of si-crystalline PV modules for any irradiance and module cell temperature. The results showed that the proposed ANN introduced a good accurate prediction for si-crystalline PV modules performance when compared with the measured values. Now, this method, based on ANNs, is going to be applied to obtain a suitable value of the power provided by a photovoltaic installation. Specifically this method is going to be applied to obtain the power provided by a particular installation, the Univer generator, since modules used in these works were the same as the ones used in this photovoltaic generator. (C) 2009 Elsevier Ltd. All rights reserved.